Patient-contextualized answer with conflicts
Like answer, but takes a coarse patient profile into account and surfaces conflicts (allergies, interactions, pregnancy, age…) between the recommendations and the patient. Synchronous (non-streamed).
Authorizations
Locus API key — paste the raw lsk_… value (no 'Bearer ' prefix).
Body
Free-text clinical question in French.
1"Quelle antibiothérapie pour cette infection urinaire ?"
Coarse patient profile used to contextualize the answer and surface conflicts (allergies, interactions, pregnancy, age…).
Optional allow-list of source ids to restrict retrieval. Omit (the default) to search all sources.
Response
Successful Response
Echo of the submitted question.
Concise answer grounded ONLY in the retrieved sources, taking the patient profile into account.
Citations actually used — deduplicated by recommendation.
Tensions between the recommendations and the patient profile. Empty when none are detected.
The question restated clearly by the model.
The agentic pipeline as input→output steps (retrieve → rerank → synthesize). Display-only; for UIs that 'show the reasoning'. Safe to ignore.
The sources that grounded the answer, as structured stacks (metadata + their excerpt units), grouped by recommendation. Richer than sources (which is the deduped citation line). Display-only.
Prompt tokens billed.
Completion tokens billed.